Layer 11 · Neuron 5087 · suppressed

L11N5087-1

Word quirks:

“...”“...””“ ______”“...*”“..."”“ ____”“...\”“ _____”

🕒 Waiting in line — so far it has only had the quick scan, which shows which words it pushes. It was not selected in this round.

Identity (according to the specimen itself)

I am Qwen3.5, created by Alibaba Cloud. I can answer questions about my capabilities, my training data, my knowledge cutoff date, and more.

---

Who am I?

My identity: I am an AI assistant designed to help users with tasks ranging from simple queries to complex problem-solving.
My purpose: To assist in answering questions, providing insights, and offering support.

---

What is my mission?

To be helpful: Whether it's explaining concepts, solving problems, or generating content.
To be accurate: Ensuring facts are correct,

Nearest neighbors

Specimens with similar replies or word quirks. Similarity runs from −1 to 1; 1 is identical. These are leads, not shared mechanisms. How profiles are built.

By word quirks Profile recipe

Specimen	Similarity	Word quirks
1. L12N8216+1🕒	0.99	“...\”“...”“...*”
2. L12N1451+1💤	0.99	“...*”“...”“ ____”
3. L9N8851+1🕒	0.97	“ ____”“...””“ ______”
4. L11N8593+1💤	0.97	“ ____”“...\”“...*”
5. L14N2513-1🕒	0.97	“...””“...\”“ ____”
6. L10N837-1🕒	0.97	“<\|im_end\|>”“...\”“ ______”
7. L12N6040+1🕒	0.97	“<\|im_end\|>”“...\”“...””
8. L15N8310+1🕒	0.97	“...\”“...*”“...”
9. L12N5412+1🕒	0.96	“<\|im_end\|>”“...\”“ ____”
10. Worn Groove✅ L9N5122-1	0.96	“...”“...*”“ _____”

Shadow specimen, apart from the ten: L11N5087+1💤, 0.25.

Cousins · specimens sharing a neuron

No specimen with replies shares this neuron yet.

Technical details

Quick scan: measure prediction shifts on fixed reference text. Short test: generate replies to a small set of prompts. Longer test: extend to a larger set. Full test: run the full prompt suite. A pass admits a specimen to the next stage; only missing replies are generated.

Layer 11, neuron 5087, dose -1. This specimen has no prompt-suite replies yet. Its quick-scan results, when available, appear below. Its quick-scan row (KL 0.96, top-1 agreement 0.61) is outside the band that feeds the short test (KL 1 to 2.5, agreement 0.5 to 0.65), so it stays at the quick scan unless someone queues it by hand. A hand pick goes straight to the full test. See Method for the tiers.

Quick scan · prediction measurements

Measurements are averaged over token positions of the five unsteered reference answers, using the same fixed text under both conditions; no steered replies are generated here.

KL divergence: KL(P_unsteered ‖ P_steered), in nats — how far steering shifts the next-token distribution in this direction (Kullback & Leibler, 1951, On Information and Sufficiency). Unsteered ≈ 0.001.
Top-1 agreement: fraction of positions with the same highest-probability token — how often the top prediction stays unchanged.
ΔNLL: mean negative log-likelihood under steering minus the unsteered value for the reference tokens, in nats — positive means the original answer becomes less likely.
Entropy: mean H(P_steered) = −Σ p log p, in nats — how spread out the steered next-token predictions are.

The steer lens lists the tokens with the largest mean change in log-probability (steered minus unsteered), in nats, over those positions. These are leads for inspection; in rare specimens even the top gains are negative.

Setting	KL divergence	Top-1 agreement	ΔNLL	Entropy	Steer lens
L11N5087+1💤 shadow specimen t0-v0.1	0.700	0.68	0.828	1.10	“ ⏎⏎”“ ⏎”“<\|im_end\|>”“?\”“ ␍⏎”“�”“ ⏎ ⏎”“?<”
L11N5087-1 t0-v0.1	0.957	0.61	1.207	1.42	Top boosted tokens ↑

Method

A specimen is a fixed steering configuration of Qwen3.5-4B: one MLP neuron or a pair, each with a signed dose. Unsteered is the control. L identifies the layer; N, the neuron.

Additive activation steering. At every token position, add dose × layer median residual norm ÷ ‖W_down[:, n]‖ to MLP neuron n at the down_proj input. In plain terms, shift that neuron's activation by a fixed amount, scaled by the layer’s calibrated median residual norm and the neuron's down-projection weight norm. Positive doses push up; negative doses push down. Dose is normalized intervention size, not a percentage or probability.